This article will be a visual representation of the data I collected, as written in my previous post.

For this visualisation, I will be using the pandas and plotly express libraries, which are imported into Jupyter Notebook using:

import pandas as pd
import plotly.express as px

Then, using the pd.read_csv function, I read the components of the csv file containing the required data.

movies = pd.read_csv('Bollywood_movies.csv')

Note: Once I had saved the data collected from BeautifulSoup into an excel sheet, I did a little bit of cleaning and sorting before exporting it into a csv file.

When called, the table looked like this.

Since the data is relatively small (9 columns and 25 entries), it kind of limited the visualisations I could do, of which I explored:

• How many top grossing movies were released each year?
• Were there any directors who had directed more than one top grossing movie?
• Which languages were preferred?

1. Comparison of World Wide Gross of Movies

As seen in this bar graph, the highest grossing movie in Bollywood is Dangal which earned around ₹2,000 crore (roughly around $311 million), closely followed by Baahubali 2, which was at ₹1,800 crore ( $278 million). Dangal earned 50% more than the 3rd most grossing movie, Bajrangi Bhaijaan.

Though the numbers are huge, this doesn’t come as a surprise as Dangal has a fantastic story line which was inspirational to everyone and anyone who watched it (this comes with no bias what so ever).

Its release in 2016 was a hit in not only India, but also around the world. I was studying in China during that time, and I remember one of my close friends telling me that she had watched the movie with her mom (who had watched it 3 times within a span of a month)!

#plotly-express #python #data-science #visualisation #bollywood #data analysis